Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1276 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1309758 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.6024. Min Act: -0.1700

Data Index: 458240 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.5241. Min Act: -0.1700

Data Index: 322615 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.4928. Min Act: -0.1700

Data Index: 179311 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.4928. Min Act: -0.1700

Data Index: 1124055 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.4614. Min Act: -0.1700

Data Index: 1095132 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.4301. Min Act: -0.1700

Data Index: 415674 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3830. Min Act: -0.1700

Data Index: 1131492 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.4144. Min Act: -0.1700

Data Index: 1292016 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3830. Min Act: -0.1700

Data Index: 888629 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3673. Min Act: -0.1700

Data Index: 306469 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3516. Min Act: -0.1700

Data Index: 844653 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3516. Min Act: -0.1700

Data Index: 98712 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3359. Min Act: -0.1700

Data Index: 795400 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.3202. Min Act: -0.1700

Data Index: 461587 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.2888. Min Act: -0.1700

Data Index: 854549 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.2888. Min Act: -0.1700

Data Index: 622817 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.2888. Min Act: -0.1700

Data Index: 727114 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.2731. Min Act: -0.1700

Data Index: 739892 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 3.6337. Min Range: -3.6337

Max Act: 3.2888. Min Act: -0.1700

Data Index: 585814 (C4 (Web Text))

Max Activating Token Index: 99